Publication Type

Journal Article

Version

acceptedVersion

Publication Date

9-2023

Abstract

Integrating low-level edge features has been proven to be effective in preserving clear boundaries of salient objects. However, the locality of edge features makes it difficult to capture globally salient edges, leading to distraction in the final predictions. To address this problem, we propose to produce distraction-free edge features by incorporating cross-scale holistic interdependencies between high-level features. In particular, we first formulate our edge features extraction process as a boundary-filling problem. In this way, we enforce edge features to focus on closed boundaries instead of those disconnected background edges. Second, we propose to explore cross-scale holistic contextual connections between every position pair of high-level feature maps regardless of their distances across different scales. It selectively aggregates features at each position based on its connections to all the others, simulating the "contrast" stimulus of visual saliency. Finally, we present a complementary features integration module to fuse low- and high-level features according to their properties. Experimental results demonstrate our proposed method outperforms previous state-of-the-art methods on the benchmark datasets, with the fast inference speed of 30 FPS on a single GPU.

Keywords

Feature extraction, Image edge detection, Object detection, Visualization, Filling, Task analysis, Convolution

Discipline

Graphics and Human Computer Interfaces | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

IEEE MultiMedia

Volume

30

Issue

3

First Page

63

Last Page

73

ISSN

1070-986X

Identifier

10.1109/MMUL.2023.3235936

Publisher

Institute of Electrical and Electronics Engineers

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/MMUL.2023.3235936

Download

Share

COinS